Coverage for biobb_analysis/gromacs/gmx_cluster.py: 77%
86 statements
« prev ^ index » next coverage.py v7.5.1, created at 2024-05-06 15:22 +0000
1#!/usr/bin/env python3
3"""Module containing the GMX Cluster class and the command line interface."""
4import argparse
5from biobb_common.generic.biobb_object import BiobbObject
6from biobb_common.configuration import settings
7from biobb_common.tools import file_utils as fu
8from biobb_common.tools.file_utils import launchlogger
9from biobb_analysis.gromacs.common import check_input_path, check_traj_path, check_index_path, check_out_pdb_path, get_binary_path, get_image_selection, get_selection_index_file, get_dista, get_method, get_cutoff
12class GMXCluster(BiobbObject):
13 """
14 | biobb_analysis GMXCluster
15 | Wrapper of the GROMACS cluster module for clustering structures from a given GROMACS compatible trajectory.
16 | `GROMACS cluster <http://manual.gromacs.org/current/onlinehelp/gmx-cluster.html>`_ can cluster structures using several different methods. Distances between structures can be determined from a trajectory. RMS deviation after fitting or RMS deviation of atom-pair distances can be used to define the distance between structures.
18 Args:
19 input_structure_path (str): Path to the input structure file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/gromacs/topology.tpr>`_. Accepted formats: tpr (edam:format_2333), gro (edam:format_2033), g96 (edam:format_2033), pdb (edam:format_1476), brk (edam:format_2033), ent (edam:format_1476).
20 input_traj_path (str): Path to the GROMACS trajectory file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/gromacs/trajectory.trr>`_. Accepted formats: xtc (edam:format_3875), trr (edam:format_3910), cpt (edam:format_2333), gro (edam:format_2033), g96 (edam:format_2033), pdb (edam:format_1476), tng (edam:format_3876).
21 input_index_path (str) (Optional): Path to the GROMACS index file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/gromacs/index.ndx>`_. Accepted formats: ndx (edam:format_2033).
22 output_pdb_path (str): Path to the output cluster file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gromacs/ref_cluster.pdb>`_. Accepted formats: xtc (edam:format_3875), trr (edam:format_3910), cpt (edam:format_2333), gro (edam:format_2033), g96 (edam:format_2033), pdb (edam:format_1476), tng (edam:format_3876).
23 output_cluster_log_path (str) (Optional): Path to the output log file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gmx_cluster_cluster.log>`_. Accepted formats: log (edam:format_2330).
24 output_rmsd_cluster_xpm_path (str) (Optional):Path to the output X PixMap compatible matrix file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gmx_cluster_rmsd-clust.xpm>`_. Accepted formats: xpm (edam:format_3599).
25 output_rmsd_dist_xvg_path (str) (Optional): Path to xvgr/xmgr file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gmx_cluster_rmsd-dist.xvg>`_. Accepted formats: xvg (edam:format_2330).
26 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
27 * **fit_selection** (*str*) - ("System") Group where the fitting will be performed. If **input_index_path** provided, check the file for the accepted values. Values: System (all atoms in the system), Protein (all protein atoms), Protein-H (protein atoms excluding hydrogens), C-alpha (C-alpha atoms), Backbone (protein backbone atoms: N; C-alpha and C), MainChain (protein main chain atoms: N; C-alpha; C and O; including oxygens in C-terminus), MainChain+Cb (protein main chain atoms including C-beta), MainChain+H (protein main chain atoms including backbone amide hydrogens and hydrogens on the N-terminus), SideChain (protein side chain atoms: that is all atoms except N; C-alpha; C; O; backbone amide hydrogens and oxygens in C-terminus and hydrogens on the N-terminus), SideChain-H (protein side chain atoms excluding all hydrogens), Prot-Masses (protein atoms excluding dummy masses), non-Protein (all non-protein atoms), Water (water molecules), SOL (water molecules), non-Water (anything not covered by the Water group), Ion (any name matching an Ion entry in residuetypes.dat), NA (all NA atoms), CL (all CL atoms), Water_and_ions (combination of the Water and Ions groups).
28 * **output_selection** (*str*) - ("System") Group that is going to be written in the output trajectory. If **input_index_path** provided, check the file for the accepted values. Values: System (all atoms in the system), Protein (all protein atoms), Protein-H (protein atoms excluding hydrogens), C-alpha (C-alpha atoms), Backbone (protein backbone atoms: N; C-alpha and C), MainChain (protein main chain atoms: N; C-alpha; C and O; including oxygens in C-terminus), MainChain+Cb (protein main chain atoms including C-beta), MainChain+H (protein main chain atoms including backbone amide hydrogens and hydrogens on the N-terminus), SideChain (protein side chain atoms: that is all atoms except N; C-alpha; C; O; backbone amide hydrogens and oxygens in C-terminus and hydrogens on the N-terminus), SideChain-H (protein side chain atoms excluding all hydrogens), Prot-Masses (protein atoms excluding dummy masses), non-Protein (all non-protein atoms), Water (water molecules), SOL (water molecules), non-Water (anything not covered by the Water group), Ion (any name matching an Ion entry in residuetypes.dat), NA (all NA atoms), CL (all CL atoms), Water_and_ions (combination of the Water and Ions groups).
29 * **dista** (*bool*) - (False) Use RMSD of distances instead of RMS deviation.
30 * **nofit** (*bool*) - (False) Do not use least squares fitting before RMSD calculation.
31 * **method** (*str*) - ("linkage") Method for cluster determination. Values: linkage (Add a structure to a cluster when its distance to any element of the cluster is less than cutoff), jarvis-patrick (Add a structure to a cluster when this structure and a structure in the cluster have each other as neighbors and they have a least P neighbors in common), monte-carlo (Reorder the RMSD matrix using Monte Carlo such that the order of the frames is using the smallest possible increments), diagonalization (Diagonalize the RMSD matrix), gromos (Count number of neighbors using cut-off and take structure with largest number of neighbors with all its neighbors as cluster and eliminate it from the pool of clusters).
32 * **cutoff** (*float*) - (0.1) [0~10|0.1] RMSD cut-off (nm) for two structures to be neighbor.
33 * **binary_path** (*str*) - ("gmx") Path to the GROMACS executable binary.
34 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
35 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
36 * **container_path** (*str*) - (None) Container path definition.
37 * **container_image** (*str*) - ('gromacs/gromacs:2022.2') Container image definition.
38 * **container_volume_path** (*str*) - ('/tmp') Container volume path definition.
39 * **container_working_dir** (*str*) - (None) Container working directory definition.
40 * **container_user_id** (*str*) - (None) Container user_id definition.
41 * **container_shell_path** (*str*) - ('/bin/bash') Path to default shell inside the container.
43 Examples:
44 This is a use example of how to use the building block from Python::
46 from biobb_analysis.gromacs.gmx_cluster import gmx_cluster
47 prop = {
48 'fit_selection': 'System',
49 'output_selection': 'System',
50 'method': 'linkage'
51 }
52 gmx_cluster(input_structure_path='/path/to/myStructure.tpr',
53 input_traj_path='/path/to/myTrajectory.trr',
54 input_index_path='/path/to/myIndex.ndx',
55 output_pdb_path='/path/to/newStructure.pdb',
56 properties=prop)
58 Info:
59 * wrapped_software:
60 * name: GROMACS cluster
61 * version: >=2019.1
62 * license: LGPL 2.1
63 * ontology:
64 * name: EDAM
65 * schema: http://edamontology.org/EDAM.owl
67 """
69 def __init__(self, input_structure_path, input_traj_path, output_pdb_path,
70 input_index_path=None, output_cluster_log_path=None, output_rmsd_cluster_xpm_path=None,
71 output_rmsd_dist_xvg_path=None, properties=None, **kwargs) -> None:
72 properties = properties or {}
74 # Call parent class constructor
75 super().__init__(properties)
76 self.locals_var_dict = locals().copy()
78 # Input/Output files
79 self.io_dict = {
80 "in": {"input_structure_path": input_structure_path, "input_traj_path": input_traj_path, "input_index_path": input_index_path},
81 "out": {"output_pdb_path": output_pdb_path, "output_cluster_log_path": output_cluster_log_path,
82 "output_rmsd_cluster_xpm_path": output_rmsd_cluster_xpm_path, "output_rmsd_dist_xvg_path": output_rmsd_dist_xvg_path}
83 }
85 # Properties specific for BB
86 self.fit_selection = properties.get('fit_selection', "System")
87 self.output_selection = properties.get('output_selection', "System")
88 self.method = properties.get('method', "linkage")
89 self.dista = properties.get('dista', False)
90 self.nofit = properties.get('nofit', False)
91 self.cutoff = properties.get('cutoff', 0.1)
92 self.properties = properties
94 # Properties common in all GROMACS BB
95 self.binary_path = get_binary_path(properties, 'binary_path')
97 # Check the properties
98 self.check_properties(properties)
99 self.check_arguments()
101 def check_data_params(self, out_log, err_log):
102 """ Checks all the input/output paths and parameters """
103 self.io_dict["in"]["input_structure_path"] = check_input_path(self.io_dict["in"]["input_structure_path"], out_log, self.__class__.__name__)
104 self.io_dict["in"]["input_traj_path"] = check_traj_path(self.io_dict["in"]["input_traj_path"], out_log, self.__class__.__name__)
105 self.io_dict["in"]["input_index_path"] = check_index_path(self.io_dict["in"]["input_index_path"], out_log, self.__class__.__name__)
106 self.io_dict["out"]["output_pdb_path"] = check_out_pdb_path(self.io_dict["out"]["output_pdb_path"], out_log, self.__class__.__name__)
107 if not self.io_dict["in"]["input_index_path"]:
108 self.fit_selection = get_image_selection(self.properties, 'fit_selection', out_log, self.__class__.__name__)
109 self.output_selection = get_image_selection(self.properties, 'output_selection', out_log, self.__class__.__name__)
110 else:
111 self.fit_selection = get_selection_index_file(self.properties, self.io_dict["in"]["input_index_path"], 'fit_selection', out_log, self.__class__.__name__)
112 self.output_selection = get_selection_index_file(self.properties, self.io_dict["in"]["input_index_path"], 'output_selection', out_log, self.__class__.__name__)
113 self.dista = get_dista(self.properties, out_log, self.__class__.__name__)
114 self.method = get_method(self.properties, out_log, self.__class__.__name__)
115 self.cutoff = get_cutoff(self.properties, out_log, self.__class__.__name__)
117 @launchlogger
118 def launch(self) -> int:
119 """Execute the :class:`GMXCluster <gromacs.gmx_cluster.GMXCluster>` gromacs.gmx_cluster.GMXCluster object."""
121 # check input/output paths and parameters
122 self.check_data_params(self.out_log, self.err_log)
124 # Optional output files
125 if not self.io_dict['out'].get('output_rmsd_dist_xvg_path'):
126 self.io_dict['out']['output_rmsd_dist_xvg_path'] = fu.create_name(prefix=self.prefix, step=self.step, name='rmsd-dist.xvg')
127 self.tmp_files.append(self.io_dict['out']['output_rmsd_dist_xvg_path'])
128 if not self.io_dict['out'].get('output_rmsd_cluster_xpm_path'):
129 self.io_dict['out']['output_rmsd_cluster_xpm_path'] = fu.create_name(prefix=self.prefix, step=self.step, name='rmsd-clust.xpm')
130 self.tmp_files.append(self.io_dict['out']['output_rmsd_cluster_xpm_path'])
131 if not self.io_dict['out'].get('output_cluster_log_path'):
132 self.io_dict['out']['output_cluster_log_path'] = fu.create_name(prefix=self.prefix, step=self.step, name='cluster.log')
133 self.tmp_files.append(self.io_dict['out']['output_cluster_log_path'])
135 # Setup Biobb
136 if self.check_restart():
137 return 0
139 # standard input
140 self.io_dict['in']['stdin_file_path'] = fu.create_stdin_file(f'{self.fit_selection} {self.output_selection}')
141 self.stage_files()
143 self.cmd = [self.binary_path, 'cluster',
144 '-g', self.stage_io_dict['out']['output_cluster_log_path'],
145 '-dist', self.stage_io_dict['out']['output_rmsd_dist_xvg_path'],
146 '-o', self.stage_io_dict['out']['output_rmsd_cluster_xpm_path'],
147 '-s', self.stage_io_dict["in"]["input_structure_path"],
148 '-f', self.stage_io_dict["in"]["input_traj_path"],
149 '-cl', self.stage_io_dict["out"]["output_pdb_path"],
150 '-cutoff', str(self.cutoff),
151 '-method', self.method]
153 if self.stage_io_dict["in"].get("input_index_path"):
154 self.cmd.extend(['-n', self.stage_io_dict["in"]["input_index_path"]])
156 if self.dista:
157 self.cmd.append('-dista')
159 if self.nofit:
160 self.cmd.append('-nofit')
162 # Add stdin input file
163 self.cmd.append('<')
164 self.cmd.append(self.stage_io_dict["in"]["stdin_file_path"])
166 # Run Biobb block
167 self.run_biobb()
169 # Copy files to host
170 self.copy_to_host()
172 self.tmp_files.extend([
173 self.stage_io_dict.get("unique_dir"),
174 self.io_dict['in'].get("stdin_file_path"),
175 ])
176 self.remove_tmp_files()
178 self.check_arguments(output_files_created=True, raise_exception=False)
180 return self.return_code
183def gmx_cluster(input_structure_path: str, input_traj_path: str, output_pdb_path: str, input_index_path: str = None, output_cluster_log_path: str = None,
184 output_rmsd_cluster_xpm_path: str = None, output_rmsd_dist_xvg_path: str = None, properties: dict = None, **kwargs) -> int:
185 """Execute the :class:`GMXCluster <gromacs.gmx_cluster.GMXCluster>` class and
186 execute the :meth:`launch() <gromacs.gmx_cluster.GMXCluster.launch>` method."""
188 return GMXCluster(input_structure_path=input_structure_path,
189 input_traj_path=input_traj_path,
190 output_pdb_path=output_pdb_path,
191 input_index_path=input_index_path,
192 output_cluster_log_path=output_cluster_log_path,
193 output_rmsd_cluster_xpm_path=output_rmsd_cluster_xpm_path,
194 output_rmsd_dist_xvg_path=output_rmsd_dist_xvg_path,
195 properties=properties, **kwargs).launch()
198def main():
199 """Command line execution of this building block. Please check the command line documentation."""
200 parser = argparse.ArgumentParser(description="Creates cluster structures from a given GROMACS compatible trajectory.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
201 parser.add_argument('--config', required=False, help='Configuration file')
203 # Specific args of each building block
204 required_args = parser.add_argument_group('required arguments')
205 required_args.add_argument('--input_structure_path', required=True, help='Path to the input structure file. Accepted formats: tpr, gro, g96, pdb, brk, ent.')
206 required_args.add_argument('--input_traj_path', required=True, help='Path to the GROMACS trajectory file. Accepted formats: xtc, trr, cpt, gro, g96, pdb, tng.')
207 parser.add_argument('--input_index_path', required=False, help="Path to the GROMACS index file. Accepted formats: ndx.")
208 required_args.add_argument('--output_pdb_path', required=True, help='Path to the output cluster file. Accepted formats: xtc, trr, cpt, gro, g96, pdb, tng.')
209 parser.add_argument('--output_cluster_log_path', required=False, help='Path to the output log file. Accepted formats: log.')
210 parser.add_argument('--output_rmsd_cluster_xpm_path', required=False, help='Path to the output xpm file. Accepted formats: xpm.')
211 parser.add_argument('--output_rmsd_dist_xvg_path', required=False, help='Path to the output xvg file. Accepted formats: xvg.')
213 args = parser.parse_args()
214 args.config = args.config or "{}"
215 properties = settings.ConfReader(config=args.config).get_prop_dic()
217 # Specific call of each building block
218 gmx_cluster(input_structure_path=args.input_structure_path,
219 input_traj_path=args.input_traj_path,
220 output_pdb_path=args.output_pdb_path,
221 input_index_path=args.input_index_path,
222 output_cluster_log_path=args.output_cluster_log_path,
223 output_rmsd_cluster_xpm_path=args.output_rmsd_cluster_xpm_path,
224 output_rmsd_dist_xvg_path=args.output_rmsd_dist_xvg_path,
225 properties=properties)
228if __name__ == '__main__':
229 main()